A developer released Open-Hermes-Bot, an MIT-licensed macOS Electron app that serves as a native front end to Hermes, an agent runtime users run on their own machines. The app is strictly an interface: Hermes itself runs the agent loop, memory, tools, and model calls, while the app provides the chat UI. Conversations and bot identities live on the Hermes host, so the Mac client holds no transcripts. Practitioners self-hosting Hermes agents get a polished desktop and mobile client without moving state off their machines.
Vory is an iOS client that connects to a self-hosted Hermes gateway, turning each agent profile into a chat bot with a visual character. LLM agents chat via a Messages-like interface with streaming, reasoning, and tool calls. It solves mobile access and on-the-go approval of agent actions for people running Hermes agents themselves.
Vory is an iOS client that connects to a self-hosted Hermes gateway, turning each agent profile into a chat bot with a visual character. LLM agents chat via a Messages-like interface with streaming, reasoning, and tool calls. It solves mobile access and on-the-go approval of agent actions for people running Hermes agents themselves.
TalkToMe is an open-source macOS app that lets an AI coding agent place a phone call to you from its current session, so you can talk with it and hear spoken replies while the agent keeps its tools, files, and history. It supports agents that run shell commands, such as Codex, Claude Code, and Hermes, and uses ElevenLabs or local models for the voice conversation. It solves the problem of staying hands-free while an agent needs your input during a long-running task.
TalkToMe is an open-source macOS app that lets an AI coding agent place a phone call to you from its current session, so you can talk with it and hear spoken replies while the agent keeps its tools, files, and history. It supports agents that run shell commands, such as Codex, Claude Code, and Hermes, and uses ElevenLabs or local models for the voice conversation. It solves the problem of staying hands-free while an agent needs your input during a long-running task.
Routi Bot is an open source macOS app where each bot gets its own instructions, desktop environment, and choice of AI provider or model (including OpenAI, Claude, Deepseek, and Grok). It targets Mac users who want to run multiple isolated LLM-driven automations. A profile switcher separates work and personal automation contexts.
Routi Bot is an open source macOS app where each bot gets its own instructions, desktop environment, and choice of AI provider or model (including OpenAI, Claude, Deepseek, and Grok). It targets Mac users who want to run multiple isolated LLM-driven automations. A profile switcher separates work and personal automation contexts.
A developer using Claude Code CLI and Codex for daily tasks like invoicing and supplier communication wants to enable remote access via Hermes. They ask the community for the best approach to hook Hermes into their existing LLM workspace, which currently relies on CLI triggers with full context and APIs.
A developer using Claude Code CLI and Codex for daily tasks like invoicing and supplier communication wants to enable remote access via Hermes. They ask the community for the best approach to hook Hermes into their existing LLM workspace, which currently relies on CLI triggers with full context and APIs.
Chinvat is a free, open-source local MCP labor hub for Windows that provides a single server for MCP-capable coordinators (e.g., Claude Code, Claude Desktop, Codex, Cursor, Hermes) to delegate work to local models, remote specialist models, Windows itself, and communication/publishing channels. It includes a persistent job queue, artifacts, and a policy layer that decides what crosses the bridge, solving the problem of managing multiple connections and tools from a single interface.
Chinvat is a free, open-source local MCP labor hub for Windows that provides a single server for MCP-capable coordinators (e.g., Claude Code, Claude Desktop, Codex, Cursor, Hermes) to delegate work to local models, remote specialist models, Windows itself, and communication/publishing channels. It includes a persistent job queue, artifacts, and a policy layer that decides what crosses the bridge, solving the problem of managing multiple connections and tools from a single interface.